With the hype and concerns around AI generated images, it’s good to build an understanding of how these images actually work. In this course, Jonathan Fernandes—an expert in Generative AI and Large Language Models—breaks down the components of text-to-image generation: text encoders, a neural network, and an autoencoder. Jonathan explains how to fine-tune models based on their own dataset and compares different popular models. He also compares various models and helps you understand the benchmarks for performance, as well as potential bias, limitations, and controversies.